Subjective Estimates
The subjective evaluation
method may be used to estimate pre-test probability. To apply
this method, the physician first remembers her personal experience
with similar patients. Then, she remembers the frequency of the
disease in those patients.
In practice, this approach
has two major problems:
It makes unrealistic
demands on one's memory of patients in the distant past and
their diagnoses.
It is prone to systematic
errors (bias) in accurately recalling one's experience.
Subjective evaluation
involves at least two problematic "heuristics" (the
technical term for an educational method in which learning takes
place through individual discovery, experimentation, or trial-and-error):
On the other hand,
"anchoring and adjustment" is a very useful heuristic
in subjective evaluation. It involves two steps:
Establish an initial
estimate based on the frequency of the disease in patients with
similar chief complaints (the "anchor").
Example: Establish
the prevalence of pulmonary embolism in 100 patients presenting
to the emergency department with pleuritic chest pain.
Adjust the estimate
upward or downward by taking into account the patient's findings
("adjustment").
Example: For
pulmonary embolism, relevant findings might include hypoxemia,
unilateral leg swelling, or a history of cancer.
Question 1.5.1
Can you
see an analogy between "anchoring and adjustment" and
Bayes' theorem?
What
part of Bayes' theorem is analogous to the anchor?
| Post-test
odds |
| Pre-test
odds |
| Likelihood
ratio |
| None
of the above |
Which
part is analogous to adjustment?
| Post-test
odds |
| Pre-test
odds |
| Likelihood
ratio |
| None
of the above |
|